© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38768
    Prev
    Next
    INDEX
    Explanations

    dialogue start tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĺĤ
    -0.12
    åĿĩçĶ±
    -0.09
    itude
    -0.09
    æĺ¯ä»Ģä¹Īåij¢
    -0.09
    åĪĨåĪ«æĺ¯
    -0.09
    交éĢļå·¥åħ·
    -0.09
    并ä¸įæĦıåij³
    -0.09
    æį®äºĨ解
    -0.09
    çļĦ羣å®ŀæĢ§
    -0.09
    ç¥Ŀ
    -0.09
    POSITIVE LOGITS
    iming
    0.09
    tors
    0.09
     mig
    0.09
    éģĴ
    0.08
    ãģ«ãĤĪãĤĭ
    0.08
     yaptıģı
    0.08
    è§Ĩè§Ĵ
    0.08
    gart
    0.08
    èĩªå·±çļĦ
    0.08
    ÑģÑĢоÑĩ
    0.08
    Activations Density 0.154%

    No Known Activations